PREFER: From Player Experience to Personalized Game Refinement

Qi Chai; Zhang Zheng; Lu Yang; Zixun Sun; Hao Wang

cs.AIOct 13, 2026

PREFER: From Player Experience to Personalized Game Refinement

Authors: Qi Chai, Zhang Zheng, Lu Yang, Zixun Sun, Hao Wang

Abstract

Understanding how large language models (LLMs) evaluate gameplay experience is important for using their feedback to guide game design. However, overall ratings alone provide limited insight into which aspects of experience are associated with these judgments and how they can inform concrete game changes. We introduce PREFER, a framework that uses a shared set of experience dimensions adapted from established psychometric questionnaires to benchmark how models evaluate gameplay and to guide persona-specific game refinement. Through these dimensions, we characterize the perspectives models offer as virtual playtesters by examining how their overall assessments relate to specific aspects of experience and to the gameplay they produce. To examine how the same dimensions can guide refinement for players with different preferences, we use personas to simulate distinct player profiles. For each persona, PREFER uses experience-preference relationships to select refinement objectives, revises game rules and their implementations, and playtests candidate games to assess experience changes and predicted preference gains. Experiments with five personas show that PREFER achieves 9.2% higher mean post-play preference ratings than the strongest evaluated baseline.

Figures & tables

Figure 1: Overview of Prefer . (a) The game suite provides rules, code, and a playground. (b) Persona preferences guide rule refinement, implementation, and playtesting. (c) Models and persona-based evaluators assess the same gameplay trajectories using shared experience dimensions and overall ratings.

Figure 2: Contract-guided rule implementation. Revised rules are translated into function contracts that guide code edits and execution checks. Failure traces guide the selection of functions to repair, and the updated code is rechecked under the same contracts.

Figure 3: Experience dimensions characterize model evaluation. (a) Associations with overall ratings reveal shared emphasis on mastery and differences across other dimensions. (b) Normalized similarity shares summarize resemblance to the five persona profiles; bold marks the largest share for each model.

Figure 4: Persona evaluation profiles and preference prediction. (a) Experience dimensions relate differently to each persona’s ratings. (b) Preference prediction from each persona’s own experience scores, comparing a persona-mean baseline, shared dimension slopes with persona indicators, and separate persona models. Lower MAE indicates better prediction; intervals show uncertainty.

Judge Model	GLM-5.3	DeepSeek-4.1flash	Kimi-K2.7	MiniMax-M2.5	Qwen3.8-Max
Group Gap	1.87	1.10	1.69	1.61	1.59
Pair Agreement	96.0	78.4	88.0	91.5	93.7

Table 1: Agreement between adjacent game groups. Group Gap is the mean rating difference, and Pair Agreement is the percentage of correctly ordered cross-group pairs.

Figure 5: Shared game preferences and local ranking differences.

Method	Preference Rate	Success Rate (%)	Execution Rate (%)	ECon	PCon
Original games	2.927	–	–	–	–
Reflexion ( Shinn et al., 2023 )	2.787	83.33	99.96	0.656	6.514
PromptBreeder ( Fernando et al., 2024 )	2.740	73.33	99.86	0.670	5.407
Cardiverse ( Li et al., 2025 )	2.820	76.67	99.52	0.658	5.991
ReCode ( Yu et al., 2025 )	3.053	83.33	99.96	0.659	6.648
Prefer	3.333	86.67	99.96	0.661	7.377

Table 2: Refinement and implementation outcomes. Original games provide the preference reference. Bold marks the best method value, including ties.

Table 8

Figure 6: Feedback-guided revision in Crazy Eights. The target persona and experience dimension remain fixed while playtesting feedback guides a new drawing mechanic.

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Dimension	GLM	DS	Kimi	MM	Qwen	E	N	S	Y	T
Goals/rules	0.12	0.06	-0.01	0.03	0.12	0.17	-0.11	0.18	0.13	0.14
Autonomy	0.44	0.20	0.17	0.24	0.35	0.34	0.34	0.11	0.33	0.29
Mastery	0.57	0.41	0.48	0.43	0.56	0.50	0.39	0.07	0.48	0.38
Curiosity	0.49	0.18	0.27	0.33	0.42	0.40	0.38	0.16	0.40	0.49
Challenge fit	0.06	0.42	0.00	0.38	0.20	0.45	0.29	0.22	0.33	0.57
Cognitive challenge	0.45	0.32	0.26	0.31	0.49	0.40	0.30	-0.04	0.45	0.35

Appendix

Table 5: Associations between experience dimensions and overall ratings. Spearman correlations characterize evaluation emphasis across models and personas. E, N, S, Y, and T denote Efficiency, Narrative, Social, System, and Thrill.

Dimension	GLM	DeepSeek	Kimi	MiniMax	Qwen
Goals/rules	0.174	-0.001	0.114	0.031	0.139
Autonomy	0.132	0.150	0.025	0.117	0.144
Mastery	0.321	0.233	0.245	0.210	0.270
Curiosity	0.236	0.042	0.121	0.122	0.062
Challenge fit	0.080	0.251	-0.005	0.134	-0.036
Cognitive challenge	0.210	0.112	0.019	0.090	0.152

Appendix

Table 6: Experience associations within games. Correlations of game-centered ranks describe how experience ratings and overall judgments vary among trajectories of the same game.

Figure 7: How evaluators use the experience rating scale. Rating distributions reveal differences in scoring levels across models, personas, and experience dimensions. Colors identify the five rating levels.

Figure 8: Scoring levels and judgments of the same play. (a) Accounting for habitual scoring differences reduces large overall-score gaps among judges with similar dimension ratings. (b,c) Authors and Palace illustrate differing evaluations of identical gameplay.

Judge	Efficiency	Narrative	Social	System	Thrill
GLM	24.3	22.4	10.1	25.3	17.9
DeepSeek	22.5	22.3	13.2	23.3	18.7
Kimi	23.0	24.2	9.9	25.2	17.7
MiniMax	21.7	22.0	8.3	22.1	25.9
Qwen	24.5	21.8	7.7	25.8	20.2

Appendix

Table 7: Relative resemblance to persona evaluation profiles. Normalized similarity shares (%) summarize the relative emphasis of each persona within a model’s evaluation profile.

Figure 9: Relative persona resemblance and its uncertainty. Normalized similarity shares show each model’s relative resemblance to the five reference profiles. The 20% line indicates equal shares; intervals show uncertainty.

Figure 10: Relations among the five personas. The panels compare agreement in overall ratings, resemblance of dimension-association profiles, and proximity of gameplay behavior. These complementary views describe different aspects of persona similarity.

Figure 12: Persona contributions to neutral-score reconstruction. Fitted weights describe how persona ratings combine to predict each neutral judge’s scores. Intervals show uncertainty in these relative contributions.

Figure 14: Similarity in evaluation emphasis and game rankings. Models can agree on which games score highly while differing in how experience dimensions relate to their overall judgments.

Figure 15: Evaluation resemblance and endorsement of model-produced play. Similarity in rating patterns shows no clear overall association with relative endorsement of a model’s gameplay. Colors and numbers identify personas.

Figure 16: Observed gameplay characteristics and overall ratings. Associations summarize how decision length and action-choice characteristics relate to scores. Thick and thin lines show individual and simultaneous uncertainty intervals.

Player Experience Inventory (PXI)
Selected construct	Trajectory-based interpretation
Goals and rules	Clarity of objectives and the rules needed to pursue them
Challenge fit	Fit between the challenge and the intended player’s experience
Progress feedback	Perceptible information about progress and consequences
Ease of control	Ease of expressing the intended game action
Autonomy	Meaningful opportunities to choose how to act

Appendix

Table 10: Experience constructs selected from two instruments. PXI supplies functional and psychosocial properties; CORGIS distinguishes sources of challenge. The selected constructs are adapted to the persona’s played trajectory.

Figure 17: Preferred refinement directions across personas. First-ranked feasible targets reveal different priorities in the refinement experiment. Plus and minus signs denote intended increases and decreases in an experience dimension.

Admission gate on the fixed pool	Adopted / 150	From feedback	Mean $\Delta y$	Imp. / Tie / Dec.
Target $\geq 0.25$ and prediction $>0$	103	10	$\mathit{+0.407}$	39 / 107 / 4
Target $\geq 0.25$ only	106	13	$+0.400$	40 / 104 / 6
Prediction $>0$ only	121	28	$+0.480$	48 / 97 / 5
Target non-decreasing and prediction $>0$	115	22	$+0.433$	44 / 101 / 5
Validity only	143	50	$+0.420$	56 / 82 / 12

Appendix

Table 11: Sensitivity of refinement outcomes to the admission rule. Alternative rules trade off the number of adopted revisions and observed preference changes. Italics identify the rule used in the refinement experiment.

User Preference Modeling

User preference modeling infers what people value from choices, behavior, and feedback to personalize recommendations, predictions, and AI actions.

See all 269 papers

Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior
Aug 17, 2026Yifan Lu, Xiaopeng Yuan, Haohan WangUser Modeling Personality Modeling in Language Models
Imperial College London · University of Illinois Urbana-Champaign
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Oct 6, 2026Jiajun Chen, Haoyu Wu, Mingda Jia +1Game-Playing Agents
HKU MMLab · The University of Hong Kong · Shenzhen Loop Area Institute
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help
Sep 12, 2026Jiahong Li, Sai Siddartha Maram, Atieh Kashani +6Game-Based Learning Educational Technology
University of California Santa Cruz Santa Cruz, USA · University of Central Florida Orlando, USA · IT University of Copenhagen Copenhagen, Denmark

Aug 17, 2026J/K move · Enter open · S save

Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior

Yifan Lu, Xiaopeng Yuan, Haohan Wang

Imperial College London · University of Illinois Urbana-Champaign

User Modeling Personality Modeling in Language Models Procedural Content Generation

Open paper AskPDF arXiv

Personalized game generation requires inferring a player's abilities and behavioral style from how they play. Large language models have made this inference more attainable than ever: an LLM can read a raw gameplay transcript and produce a fluent, plausible profile of the player. Plausible, however, is not verified, and verification is precisely what the field lacks: latent traits are unobservable; questionnaires provide noisy proxies and become circular when self-reports are used to validate behavior-based inference; and behavior itself is ambiguous without context -- a player who never collects an item may not want it, or may never have had the chance. We address both problems. First, we construct a synthetic player population whose traits are ground truth by construction: each trait is an explicit bot parameter, accepted only after controlled manipulation produces consistent, trait-specific behavioral change. Unlike prior parameter-recovery work that inverts a known decision model, our benchmark evaluates policy-agnostic inference from behavioral transcripts alone. Second, we introduce an opportunity-aware decision-moment representation that disentangles preference from the chance to express it; ablating it selectively degrades opportunity-dependent traits. On this benchmark, few-shot LLM inference outperforms embedding- and rule-based baselines on most traits, though feature-based supervised regressors remain stronger overall. Finally, we close the loop: inferred profiles drive difficulty adaptation, evaluated against ground-truth references and mismatched-profile controls, and an exploratory human study examines whether these findings transfer to real players.

Abstract

User Preference Modeling

Explore similar work

Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior

Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help